© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8001
    Prev
    Next
    INDEX
    Explanations

    The <specific noun>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -1.72
     télécommande
    -1.56
    蛻
    -1.48
    鋁
    -1.40
    も行
    -1.35
    艱
    -1.34
    气息
    -1.33
    områ
    -1.31
    說的
    -1.30
    橢
    -1.30
    POSITIVE LOGITS
     recently
    1.77
     gdyż
    1.61
    ="
    1.56
    </b>
    1.56
    我只
    1.55
     but
    1.48
    ですが
    1.45
     limão
    1.42
    "><
    1.42
     as
    1.42
    Activations Density 0.234%

    No Known Activations